INDEX

Explanations

the word "fake" in the text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bonbons

-0.61

 Arrived

-0.49

 Muffins

-0.49

 prunes

-0.47

 للاسماء

-0.45

titudine

-0.44

sightly

-0.43

 Memoriam

-0.43

pencer

-0.41

 Surprisingly

-0.41

POSITIVE LOGITS

 fake

0.99

fake

0.96

 Fake

0.85

Fake

0.82

 maksi

0.76

FAKE

0.71

 faking

0.70

 fakes

0.67

 territo

0.65

 saad

0.64

Activations Density 0.098%

the word "fake" in the text

No Comments

No Known Activations